conceptbed.github.io/index.html at main · ConceptBed/conceptbed.github.io · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
<!DOCTYPE html>
<html>

<head>
  <meta charset="utf-8">
  <meta name="description"
    content="Large-scale concept learning evaluations for personalized text-to-image diffusion models.">
  <meta name="keywords" content="ConceptBed, Concept Learning, Diffusion Models, Textual Inversion">
  <meta name="viewport" content="width=device-width, initial-scale=1">
  <title>ConceptBed</title>

  <!-- Google tag (gtag.js) -->
  <script async src="https://www.googletagmanager.com/gtag/js?id=G-YRSQ1J8HYF"></script>
  <script>
    window.dataLayer = window.dataLayer || [];
    function gtag() { dataLayer.push(arguments); }
    gtag('js', new Date());

    gtag('config', 'G-YRSQ1J8HYF');
  </script>


  <link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">

  <link rel="stylesheet" href="./static/css/bulma.min.css">
  <link rel="stylesheet" href="./static/css/bulma-carousel.min.css">
  <link rel="stylesheet" href="./static/css/bulma-slider.min.css">
  <link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
  <link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
  <link rel="stylesheet" href="./static/css/index.css">
  <link rel="icon" href="./static/images/favicon.svg">

  <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
  <script defer src="./static/js/fontawesome.all.min.js"></script>
  <script src="./static/js/bulma-carousel.min.js"></script>
  <script src="./static/js/bulma-slider.min.js"></script>
  <script src="./static/js/index.js"></script>
  <script type="text/x-mathjax-config">
    MathJax.Hub.Config({tex2jax: {inlineMath: [['$','$'], ['\\(','\\)']]}});
  </script>
  <script type="text/javascript"
    src="http://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
    </script>

  <style>
    #project-previews {
      display: flex;
      justify-content: space-around;
      margin: 20px 0;
      padding: 20px;
    }

    .project {
      width: 300px;
      /* Adjust as needed */
      height: 320px;
      /* Adjust as needed */
      border: 1px solid #ddd;
      text-align: center;
      transition: transform 0.3s ease;
    }

    .project img {
      width: 100%;
      /* Make image fill the container */
      height: 200px;
      /* Adjust height as needed */
      object-fit: cover;
    }

    .project h3,
    .project p {
      margin: 5px 0;
    }

    /* Hover effect */
    .project:hover {
      transform: scale(1.05);
      box-shadow: 0 5px 15px rgba(0, 0, 0, 0.2);
    }

    #project-previews a.project {
      text-decoration: none;
      /* Remove underline from links */
      color: inherit;
      /* Use the parent's text color */
      display: block;
      /* Make the anchor tag behave like a block element */
    }

    #project-previews a.project:hover {
      transform: scale(1.05);
      box-shadow: 0 5px 15px rgba(0, 0, 0, 0.2);
    }
  </style>


</head>

<body>

  <nav class="navbar" role="navigation" aria-label="main navigation">
    <div class="navbar-brand">
      <a role="button" class="navbar-burger" aria-label="menu" aria-expanded="false">
        <span aria-hidden="true"></span>
        <span aria-hidden="true"></span>
        <span aria-hidden="true"></span>
      </a>
    </div>
    <div class="navbar-menu">
      <div class="navbar-start" style="flex-grow: 1; justify-content: center;">
        <a class="navbar-item" href="https://maitreyapatel.com/">
          <span class="icon">
            <i class="fas fa-home"></i>
          </span>
        </a>
        <div class="navbar-item has-dropdown is-hoverable">
          <a class="navbar-link">
            More Research
          </a>
          <div class="navbar-dropdown">
            <a class="navbar-item" href="https://eclipse-t2i.vercel.app/">
              ECLIPSE (Efficient T2I)
            </a>
            <a class="navbar-item" href="https://wouaf.vercel.app">
              WOUAF (Secure T2I)
            </a>
          </div>
        </div>
      </div>

    </div>
  </nav>


  <section class="hero">
    <div class="hero-body">
      <div class="container is-max-desktop">
        <div class="columns is-centered">
          <div class="column has-text-centered">
            <h1 class="title is-1 publication-title">ConceptBed <p style="font-size:xx-large;">Evaluating Concept
                Learning Abilities of
                Text-to-Image
                Diffusion Models</p>
            </h1>
            <div class="is-size-5 publication-authors">
              <span class="author-block">
                <a href="https://maitreyapatel.com">Maitreya Patel</a>,</span>
              <span class="author-block">
                <a href="https://www.tejasgokhale.com/">Tejas Gokhale</a>,
              </span>
              <span class="author-block">
                <a href="https://www.public.asu.edu/~cbaral/">Chitta Baral</a>,
              </span>
              <span class="author-block">
                <a href="https://yezhouyang.engineering.asu.edu/">Yezhou Yang</a>
              </span>
            </div>
            <div class="is-size-5 publication-authors">
              Arizona State University
            </div>
            <br>
            <div class="is-size-5 publication-authors">
              <b>AAAI'24 (NeurIPS fast-track)</b> | NeurIPS'23 Workshop on Diffusion Models
            </div>
            <br>
            <div class="column has-text-centered">
              <div class="publication-links">
                <!-- PDF Link. -->
                <span class="link-block">
                  <a href="./AAAI_camera_ready.pdf"
                    class="external-link button is-normal is-rounded is-dark">
                    <span class="icon">
                      <i class="fas fa-file-pdf"></i>
                    </span>
                    <span>PDF (AAAI)</span>
                  </a>
                </span>
                <span class="link-block">
                  <a href="https://arxiv.org/abs/2306.04695" class="external-link button is-normal is-rounded is-dark">
                    <span class="icon">
                      <i class="fas fa-file-pdf"></i>
                    </span>
                    <span>arXiv</span>
                  </a>
                </span>
                <span class="link-block">
                  <a href="https://github.com/ConceptBed/evaluations"
                    class="external-link button is-normal is-rounded is-dark">
                    <span class="icon">
                      <i class="fab fa-github"></i>
                    </span>
                    <span>Code</span>
                  </a>
                </span>
                <!-- Dataset Link. -->
                <span class="link-block">
                  <a href="data.html" class="external-link button is-normal is-rounded is-dark">
                    <span class="icon">
                      <i class="fa fa-database"></i>
                    </span>
                    <span>Data</span>
                  </a>
                </span>
                <!-- Online Dataset Bowese. -->
                <span class="link-block">
                  <a href="https://huggingface.co/spaces/mpatel57/ConceptBed"
                    class="external-link button is-normal is-rounded is-dark">
                    <span class="icon">
                      <i class="far fa-images"></i>
                    </span>
                    <span>Results Explorer</span>
                  </a>
                </span>
                <span class="link-block">
                  <a href="https://conceptbed-leaderboard.vercel.app/"
                    class="external-link button is-normal is-rounded is-dark">
                    <span class="icon">
                      <i class="far fa-solid fa-arrow-trend-up"></i>
                    </span>
                    <span>Leaderboard (NEW!)</span>
                  </a>
                </span>
              </div>

            </div>
          </div>
        </div>
      </div>
    </div>
  </section>

  <section class="hero teaser">
    <div class="container is-max-desktop">
      <div class="is-centered has-text-centered">
        <div class="hero-body">
          <img src="./static/images/introduction_cl.png" width="60%">
        </div>
      </div>
    </div>
  </section>


  <section class="section">
    <div class="container is-max-desktop">
      <!-- Abstract. -->
      <div class="columns is-centered has-text-centered">
        <div class="column is-four-fifths">
          <h2 class="title is-3">Abstract</h2>
          <div class="content has-text-justified">
            <p>
              The ability to understand visual concepts and replicate and compose these concepts from images is a
              central goal for computer vision. Recent advances in text-to-image (T2I) models have lead to high
              definition and realistic image quality generation by learning from large databases of images and their
              descriptions. However, the evaluation of T2I models has focused on photorealism and limited qualitative
              measures of visual understanding. To quantify the ability of T2I models in learning and synthesizing novel
              visual concepts, we introduce <b style="font-size: large;">ConceptBed</b>, a large-scale dataset that
              consists of 284 unique visual
              concepts, 5K unique concept compositions, and 33K composite text prompts. Along with the dataset, we
              propose an evaluation metric, <u>C</u>oncept <u>C</u>onfidence <u>D</u>eviation (<b
                style="font-size: large;">CCD</b>), that uses the confidence of
              oracle
              concept classifiers to measure the alignment between concepts generated by T2I generators and concepts
              contained in ground truth images. We evaluate visual concepts that are either objects, attributes, or
              styles, and also evaluate four dimensions of compositionality: counting, attributes, relations, and
              actions. Our human study shows that <b style="font-size: large;">CCD</b> is <i><u>highly
                  correlated</u></i> with human
              understanding of concepts. Our
              results point to a trade-off between learning the concepts and preserving the compositionality which
              existing approaches struggle to overcome.
            </p>
          </div>
        </div>
      </div>
      <!--/ Abstract. -->

      <br>
      <br>
      <br>

      <div class="columns is-centered has-text-centered">
        <div class="column is-four-fifths">
          <img src="./static/images/database_overview.png">
          <br>
          <br>
          <br>
          <img src="./static/images/qualitative_example-min.png">
        </div>
      </div>

    </div>
  </section>


  <section class="footer" id="BibTeX">
    <div class="container is-max-desktop content">
      <h2 class="title">BibTeX</h2>
      <pre><code>@article{patel2023conceptbed,
  author    = {Patel, Maitreya and Gokhale, Tejas and Baral, Chitta and Yang, Yezhou},
  title     = {ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models},
  year      = {2023},
}</code></pre>
    </div>
  </section>

  <section class="section">
    <div class="container is-max-desktop">
      <!-- Abstract. -->
      <div class="columns is-centered has-text-centered">
        <div class="column is-four-fifths">
          <h2 class="title is-3">Relevant Projects</h2>
        </div>
      </div>
    </div>
  </section>
  <section class="section" id="project-previews">
    <a href="https://eclipse-t2i.vercel.app" class="project">
      <img src="./static/images/eclipse.png">
      <h3 class="title is-5">ECLIPSE</h3>
      <p>A Resource-Efficient Text-to-Image Prior for Image Generations</p>
    </a>

    <a href="https://wouaf.vercel.app/" class="project">
      <img src="./static/images/wouaf.png">
      <h3 class="title is-5">WOUAF</h3>
      <p>Weight Modulation for User Attribution and Fingerprinting in T2I Models. </p>
    </a>
  </section>


  <footer class="footer">
    <div class="container">
      <div class="content has-text-centered">
        <a class="icon-link" href="https://arxiv.org/abs/2306.04695">
          <i class="fas fa-file-pdf"></i>
        </a>
        <a class="icon-link" href="https://github.com/ConceptBed" class="external-link" disabled>
          <i class="fab fa-github"></i>
        </a>
      </div>
      <div class="columns is-centered">
        <div class="content">
          <p>
            This website template is inspired from <a href="https://github.com/nerfies/nerfies.github.io">Nerfies</a>
            and
            modified by <a href="https://maitreyapatel.com">Maitreya Patel</a>.
            <br>
            The website source code is available at: <a href="https://github.com/ConceptBed/ConceptBed">GitHub</a>
          </p>
        </div>
      </div>
    </div>
  </footer>

</body>

</html>