Abstract:Large-scale vision-language pre-trained (VLP) models (e.g., CLIP) are renowned for their versatility, as they can be applied to diverse applications in a zero-shot setup. However, when these models are used in specific domains, their performance often falls short due to domain gaps or the under-representation of these domains in the training data. While fine-tuning VLP models on custom datasets with human-annotated labels can address this issue, annotating even a small-scale dataset (e.g., 100k samples) can be an expensive endeavor, often requiring expert annotators if the task is complex. To address these challenges, we propose LatteCLIP, an unsupervised method for fine-tuning CLIP models on classification with known class names in custom domains, without relying on human annotations. Our method leverages Large Multimodal Models (LMMs) to generate expressive textual descriptions for both individual images and groups of images. These provide additional contextual information to guide the fine-tuning process in the custom domains. Since LMM-generated descriptions are prone to hallucination or missing details, we introduce a novel strategy to distill only the useful information and stabilize the training. Specifically, we learn rich per-class prototype representations from noisy generated texts and dual pseudo-labels. Our experiments on 10 domain-specific datasets show that LatteCLIP outperforms pre-trained zero-shot methods by an average improvement of +4.74 points in top-1 accuracy and other state-of-the-art unsupervised methods by +3.45 points.
Abstract:Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images. Yet, the independent process of image generation in these prevailing methods leads to challenges in maintaining multiple-view consistency. To address this, we introduce ViewFusion, a novel, training-free algorithm that can be seamlessly integrated into existing pre-trained diffusion models. Our approach adopts an auto-regressive method that implicitly leverages previously generated views as context for the next view generation, ensuring robust multi-view consistency during the novel-view generation process. Through a diffusion process that fuses known-view information via interpolated denoising, our framework successfully extends single-view conditioned models to work in multiple-view conditional settings without any additional fine-tuning. Extensive experimental results demonstrate the effectiveness of ViewFusion in generating consistent and detailed novel views.
Abstract:Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability in the output space of the generated images. We propose a novel learning method for text-guided image editing, namely \texttt{iEdit}, that generates images conditioned on a source image and a textual edit prompt. As a fully-annotated dataset with target images does not exist, previous approaches perform subject-specific fine-tuning at test time or adopt contrastive learning without a target image, leading to issues on preserving the fidelity of the source image. We propose to automatically construct a dataset derived from LAION-5B, containing pseudo-target images with their descriptive edit prompts given input image-caption pairs. This dataset gives us the flexibility of introducing a weakly-supervised loss function to generate the pseudo-target image from the latent noise of the source image conditioned on the edit prompt. To encourage localised editing and preserve or modify spatial structures in the image, we propose a loss function that uses segmentation masks to guide the editing during training and optionally at inference. Our model is trained on the constructed dataset with 200K samples and constrained GPU resources. It shows favourable results against its counterparts in terms of image fidelity, CLIP alignment score and qualitatively for editing both generated and real images.
Abstract:Long-form video understanding requires designing approaches that are able to temporally localize activities or language. End-to-end training for such tasks is limited by the compute device memory constraints and lack of temporal annotations at large-scale. These limitations can be addressed by pre-training on large datasets of temporally trimmed videos supervised by class annotations. Once the video encoder is pre-trained, it is common practice to freeze it during fine-tuning. Therefore, the video encoder does not learn temporal boundaries and unseen classes, causing a domain gap with respect to the downstream tasks. Moreover, using temporally trimmed videos prevents to capture the relations between different action categories and the background context in a video clip which results in limited generalization capacity. To address these limitations, we propose a novel post-pre-training approach without freezing the video encoder which leverages language. We introduce a masked contrastive learning loss to capture visio-linguistic relations between activities, background video clips and language in the form of captions. Our experiments show that the proposed approach improves the state-of-the-art on temporal action localization, few-shot temporal action localization, and video language grounding tasks.
Abstract:Cross-modal recipe retrieval has recently gained substantial attention due to the importance of food in people's lives, as well as the availability of vast amounts of digital cooking recipes and food images to train machine learning models. In this work, we revisit existing approaches for cross-modal recipe retrieval and propose a simplified end-to-end model based on well established and high performing encoders for text and images. We introduce a hierarchical recipe Transformer which attentively encodes individual recipe components (titles, ingredients and instructions). Further, we propose a self-supervised loss function computed on top of pairs of individual recipe components, which is able to leverage semantic relationships within recipes, and enables training using both image-recipe and recipe-only samples. We conduct a thorough analysis and ablation studies to validate our design choices. As a result, our proposed method achieves state-of-the-art performance in the cross-modal recipe retrieval task on the Recipe1M dataset. We make code and models publicly available.
Abstract:Image captioning is an interdisciplinary research problem that stands between computer vision and natural language processing. The task is to generate a textual description of the content of an image. The typical model used for image captioning is an encoder-decoder deep network, where the encoder captures the essence of an image while the decoder is responsible for generating a sentence describing the image. Attention mechanisms can be used to automatically focus the decoder on parts of the image which are relevant to predict the next word. In this paper, we explore different decoders and attentional models popular in neural machine translation, namely attentional recurrent neural networks, self-attentional transformers, and fully-convolutional networks, which represent the current state of the art of neural machine translation. The image captioning module is available as part of SOCKEYE at https://github.com/awslabs/sockeye which tutorial can be found at https://awslabs.github.io/sockeye/image_captioning.html .
Abstract:In many computer vision tasks, the relevant information to solve the problem at hand is mixed to irrelevant, distracting information. This has motivated researchers to design attentional models that can dynamically focus on parts of images or videos that are salient, e.g., by down-weighting irrelevant pixels. In this work, we propose a spatiotemporal attentional model that learns where to look in a video directly from human fixation data. We model visual attention with a mixture of Gaussians at each frame. This distribution is used to express the probability of saliency for each pixel. Time consistency in videos is modeled hierarchically by: 1) deep 3D convolutional features to represent spatial and short-term time relations and 2) a long short-term memory network on top that aggregates the clip-level representation of sequential clips and therefore expands the temporal domain from few frames to seconds. The parameters of the proposed model are optimized via maximum likelihood estimation using human fixations as training data, without knowledge of the action in each video. Our experiments on Hollywood2 show state-of-the-art performance on saliency prediction for video. We also show that our attentional model trained on Hollywood2 generalizes well to UCF101 and it can be leveraged to improve action classification accuracy on both datasets.
Abstract:This paper presents a novel framework for visual object recognition using infinite-dimensional covariance operators of input features in the paradigm of kernel methods on infinite-dimensional Riemannian manifolds. Our formulation provides in particular a rich representation of image features by exploiting their non-linear correlations. Theoretically, we provide a finite-dimensional approximation of the Log-Hilbert-Schmidt (Log-HS) distance between covariance operators that is scalable to large datasets, while maintaining an effective discriminating capability. This allows us to efficiently approximate any continuous shift-invariant kernel defined using the Log-HS distance. At the same time, we prove that the Log-HS inner product between covariance operators is only approximable by its finite-dimensional counterpart in a very limited scenario. Consequently, kernels defined using the Log-HS inner product, such as polynomial kernels, are not scalable in the same way as shift-invariant kernels. Computationally, we apply the approximate Log-HS distance formulation to covariance operators of both handcrafted and convolutional features, exploiting both the expressiveness of these features and the power of the covariance representation. Empirically, we tested our framework on the task of image classification on twelve challenging datasets. In almost all cases, the results obtained outperform other state of the art methods, demonstrating the competitiveness and potential of our framework.
Abstract:This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using any ground-truth bounding boxes for training. The key idea is to analyze the change in the recognition scores when artificially masking out different regions of the image. The masking out of a region that includes the object typically causes a significant drop in recognition score. This idea is embedded into an agglomerative clustering technique that generates self-taught localization hypotheses. Our object localization scheme outperforms existing proposal methods in both precision and recall for small number of subwindow proposals (e.g., on ILSVRC-2012 it produces a relative gain of 23.4% over the state-of-the-art for top-1 hypothesis). Furthermore, our experiments show that the annotations automatically-generated by our method can be used to train object detectors yielding recognition results remarkably close to those obtained by training on manually-annotated bounding boxes.
Abstract:This paper presents a general vector-valued reproducing kernel Hilbert spaces (RKHS) framework for the problem of learning an unknown functional dependency between a structured input space and a structured output space. Our formulation encompasses both Vector-valued Manifold Regularization and Co-regularized Multi-view Learning, providing in particular a unifying framework linking these two important learning approaches. In the case of the least square loss function, we provide a closed form solution, which is obtained by solving a system of linear equations. In the case of Support Vector Machine (SVM) classification, our formulation generalizes in particular both the binary Laplacian SVM to the multi-class, multi-view settings and the multi-class Simplex Cone SVM to the semi-supervised, multi-view settings. The solution is obtained by solving a single quadratic optimization problem, as in standard SVM, via the Sequential Minimal Optimization (SMO) approach. Empirical results obtained on the task of object recognition, using several challenging datasets, demonstrate the competitiveness of our algorithms compared with other state-of-the-art methods.