DeViL: Decoding Vision features into Language

• URL: http://arxiv.org/abs/2309.01617v1
• Date: Mon, 4 Sep 2023 13:59:55 GMT
• Title: DeViL: Decoding Vision features into Language
• Authors: Meghal Dani, Isabel Rio-Torto, Stephan Alaniz, Zeynep Akata
• Abstract summary: Post-hoc explanation methods have often been criticised for abstracting away the decision-making process of deep neural networks. In this work, we would like to provide natural language descriptions for what different layers of a vision backbone have learned. We train a transformer network to translate individual image features of any vision layer into a prompt that a separate off-the-shelf language model decodes into natural language.
• Score: 53.88202366696955
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Post-hoc explanation methods have often been criticised for abstracting away the decision-making process of deep neural networks. In this work, we would like to provide natural language descriptions for what different layers of a vision backbone have learned. Our DeViL method decodes vision features into language, not only highlighting the attribution locations but also generating textual descriptions of visual features at different layers of the network. We train a transformer network to translate individual image features of any vision layer into a prompt that a separate off-the-shelf language model decodes into natural language. By employing dropout both per-layer and per-spatial-location, our model can generalize training on image-text pairs to generate localized explanations. As it uses a pre-trained language model, our approach is fast to train, can be applied to any vision backbone, and produces textual descriptions at different layers of the vision network. Moreover, DeViL can create open-vocabulary attribution maps corresponding to words or phrases even outside the training scope of the vision model. We demonstrate that DeViL generates textual descriptions relevant to the image content on CC3M surpassing previous lightweight captioning models and attribution maps uncovering the learned concepts of the vision backbone. Finally, we show DeViL also outperforms the current state-of-the-art on the neuron-wise descriptions of the MILANNOTATIONS dataset. Code available at https://github.com/ExplainableML/DeViL

Related papers

• Using Multimodal Deep Neural Networks to Disentangle Language from Visual Aesthetics [8.749640179057469]
  We use linear decoding over the learned representations of unimodal vision, unimodal language, and multimodal deep neural network (DNN) models to predict human beauty ratings of naturalistic images. We show that unimodal vision models (e.g. SimCLR) account for the vast majority of explainable variance in these ratings. Language-aligned vision models (e.g. SLIP) yield small gains relative to unimodal vision. Taken together, these results suggest that whatever words we may eventually find to describe our experience of beauty, the ineffable computations of feedforward perception may provide sufficient foundation for that experience.
  arXiv  Detail & Related papers  (2024-10-31T03:37:21Z)
• Beyond Text: Frozen Large Language Models in Visual Signal Comprehension [34.398976855955404]
  Vision-to-Language Tokenizer, abbreviated as V2T Tokenizer, transforms an image into a foreign language'' with the combined aid of an encoder-decoder, the LLM vocabulary, and a CLIP model. We undertake rigorous experiments to validate our method, encompassing understanding tasks like image recognition, image captioning, and visual question answering, as well as image denoising tasks like inpainting, outpainting, deblurring, and shift restoration.
  arXiv  Detail & Related papers  (2024-03-12T17:59:51Z)
• Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization [52.935150075484074]
  We introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language. The resulting visual tokens encompass high-level semantics worthy of a word and also support dynamic sequence length varying from the image. This unification empowers LaVIT to serve as an impressive generalist interface to understand and generate multi-modal content simultaneously.
  arXiv  Detail & Related papers  (2023-09-09T03:01:38Z)
• Seeing in Words: Learning to Classify through Language Bottlenecks [59.97827889540685]
  Humans can explain their predictions using succinct and intuitive descriptions. We show that a vision model whose feature representations are text can effectively classify ImageNet images.
  arXiv  Detail & Related papers  (2023-06-29T00:24:42Z)
• Universal Multimodal Representation for Language Understanding [110.98786673598015]
  This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of images either from a light topic-image lookup table extracted over the existing sentence-image pairs. Then, the text and images are encoded by a Transformer encoder and convolutional neural network, respectively.
  arXiv  Detail & Related papers  (2023-01-09T13:54:11Z)
• VL-BEiT: Generative Vision-Language Pretraining [107.25298505511184]
  We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Specifically, we perform masked vision-language modeling on image-text pairs, masked language modeling on texts, and masked image modeling on images.
  arXiv  Detail & Related papers  (2022-06-02T16:14:19Z)
• Align before Fuse: Vision and Language Representation Learning with Momentum Distillation [52.40490994871753]
  We introduce a contrastive loss to representations BEfore Fusing (ALBEF) through cross-modal attention. We propose momentum distillation, a self-training method which learns from pseudo-targets produced by a momentum model. ALBEF achieves state-of-the-art performance on multiple downstream vision-language tasks.
  arXiv  Detail & Related papers  (2021-07-16T00:19:22Z)
• Learning Visual Representations with Caption Annotations [19.24013129952071]
  We propose a proxy task to learn visual representations over image-caption pairs. ICMLM consists in predicting masked words in captions by relying on visual cues. Our experiments confirm that image captions can be leveraged to inject global and localized semantic information into visual representations.
  arXiv  Detail & Related papers  (2020-08-04T08:04:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.