Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a "bag of words" behavior. At the same time, Large Vision-Language Models (LVLMs), which combine vision encoders with LLMs, have been shown to be capable of detailed vision-language reasoning, yet their autoregressive nature renders them less suitable for discriminative tasks.In this work, we propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs that results in strong discriminative and compositional capabilities. Essentially, our approach converts a generative LVLM into a discriminative one, unlocking its capability for powerful image-text discrimination combined with enhanced language understanding.Our contributions include (1) A carefully designed training/optimization framework that utilizes image-text pairs of variable length and granularity for training the model with both contrastive and next-token prediction losses. This is accompanied by ablation studies that justify the necessity of our framework’s components. (2) A parameter-efficient adaptation method using a combination of soft prompting and LoRA adapters. (3) Significant improvements over state-of-the-art CLIP-like models of similar size, including standard image-text retrieval benchmarks and notable gains in compositionality.

Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding, manifesting bag-of-words behaviour. These limitations are reinforced by their dual-encoder design, which induces a modality gap. Additionally, the reliance on vast web-collected data corpora for training makes the process computationally expensive and introduces significant privacy concerns. To address these limitations, in this work, we challenge the necessity of vision encoders for retrieval tasks by introducing a \textit{vision-free, single-encoder} retrieval pipeline. Departing from the traditional text-to-image retrieval paradigm, we migrate to a text-to-text paradigm with the assistance of VLLM-generated structured image descriptions. We demonstrate that this paradigm shift has significant advantages, including a substantial reduction of the modality gap, improved compositionality, and better performance on short and long caption queries, all attainable with only two hours of calibration on two GPUs. Additionally, substituting raw images with textual descriptions introduces a more privacy-friendly alternative for retrieval. To further assess generalisation and address some of the shortcomings of prior compositionality benchmarks, we release two benchmarks derived from Flickr30k and COCO, containing diverse compositional queries made of short captions, which we coin subFlickr and subCOCO. Our vision-free retriever matches and often surpasses traditional multimodal models. Importantly, our approach achieves state-of-the-art zero-shot performance on multiple retrieval and compositionality benchmarks, with models as small as 0.3B parameters.

This work aims to compress the vision tokens of an LVLM into a representation that is simultaneously suitable for (a) generative and (b) discriminative tasks, (c) is nearly lossless, and (d) storage-efficient. To this end, we propose C&C, a novel compression method that leverages the LVLM itself for task-agnostic visual token compression. Unlike prior methods that perform token reduction on-the-fly, our approach offloads computation to a dedicated, upfront indexing stage, effectively decoupling compression from generation. This enables learning more powerful representations for generation during inference. At the core of C&C is a ``double-forward pass'' training strategy. During the first forward pass, the LLM (of the LVLM) creates a bottleneck by compressing the dense visual tokens into a few summary tokens. Subsequently, the second forward pass processes the language instruction(s) alongside the summary tokens, used as a direct replacement for the image ones. The training of C&C is guided by two key losses: an autoregressive loss applied after the second pass that provides a direct optimization objective for reconstructing the original information flow, and a contrastive loss applied after the first pass to bolster the representational strength of the summary tokens, particularly for discriminative tasks. Moreover, we propose stage-specific adapters for further enhancing performance. C&C produces highly informative compressed representations. An in-depth ablation study confirms the efficacy of our approach. For generative tasks, we achieve a 2x higher compression rate without compromising capabilities, setting a new state-of-the-art. For discriminative tasks, we establish new state-of-the-art results on image retrieval and compositionality benchmarks.

Despite noise and caption quality having been acknowledged as important factors impacting vision-language contrastive pre-training, in this paper, we show that the full potential of improving the training process by addressing such issues is yet to be realized. Specifically, we firstly study and analyze two issues affecting training: incorrect assignment of negative pairs, and low caption quality and diversity. Then, we devise effective solutions for addressing both problems, which essentially require training with multiple true positive pairs. Finally, we propose training with sigmoid loss to address such a requirement. We show very large gains over the current state-of-the-art for both image recognition (~ +6% on average over 11 datasets) and image retrieval (~ + 19% on Flickr30k and ~ + 15% on MSCOCO).

Current Vision-Language (VL) models owe their success to large-scale pre-training on webcollected data, which in turn requires highcapacity architectures and large compute resources for training.We posit that when the downstream tasks are known in advance, which is in practice common, the pretraining process can be aligned to the downstream domain, leading to more efficient and accurate models, while shortening the pretraining step.To this end, we introduce a domain-aligned pretraining strategy that, without additional data collection, improves the accuracy on a domain of interest, herein, that of human activities, while largely preserving the generalist knowledge.At the core of our approach stands a new LLM-based method that, provided with a simple set of concept seeds, produces a concept hierarchy with high coverage of the target domain.The concept hierarchy is used to filter a large-scale webcrawled dataset and, then, enhance the resulting instances with targeted synthetic labels.We study in depth how to train such approaches and their resulting behavior.We further show generalization to video-based data by introducing a fast adaptation approach for transitioning from a static (image) model to a dynamic one (i.e. with temporal modeling).On the domain of interest, our approach significantly outperforms models trained on up to 60× more samples and between 10 -100× shorter training schedules for image retrieval, video retrieval and action recognition.Code will be released.

Current post-training quantization methods for LLMs compress the weights down to 4-bits, with moderate to low degradation in accuracy. However, further reducing the number of bits or accelerating the network while avoiding large accuracy drops, especially for smaller, sub 7B models, remains an actively researched and open problem. To address this, in this work, we introduce Quantization with Binary Bases (QBB), a new approach for low-bit quantization that effectively removes (nearly) all multiplications, reducing the implementation to summations. Our novel approach works by decomposing the original weights into a set of binary (1-bit) matrices using an iterative process. For a given layer, starting from a weight matrix, we first construct an initial approximation using an analytical solution, where each new binary matrix, paired with a scaling vector, approximates the residual error of the previous estimation. Secondly, using gradient descent and a progressive learning curriculum, we find the optimal set of binary matrices and scaling vectors that minimize the $\ell_2$ distance between the produced approximation and original weights. Thirdly, as previous steps are input agnostic, we holistically optimize the scaling vectors alone, calibrating them in student-teacher fashion, with the teacher providing both the data, by autoregressive generation starting from a random token, and the target logits. When evaluated across multiple LLM families, our approach matches and outperforms all prior works, setting a new state-of-the-art result using a summation-only based approach.

Vision-Language (V-L) models trained with contrastive learning to align the visual and language modalities have been shown to be strong few-shot learners. Soft prompt learning is the method of choice for few-shot downstream adaption aiming to bridge the modality gap caused by the distribution shift induced by the new domain. While parameter-efficient, prompt learning still requires access to the model weights and can be computationally infeasible for large models with billions of parameters. To address these shortcomings, in this work, we describe a black-box method for V-L few-shot adaptation that (a) operates on pre-computed image and text features and hence works without access to the model’s weights, (b) it is orders of magnitude faster at training time, (c) it is amenable to both supervised and unsupervised training, and (d) it can be even used to align image and text features computed from uni-modal models. To achieve this, we propose Linear Feature Alignment (LFA), a simple linear approach for V-L re-alignment in the target domain. LFA is initialized from a closed-form solution to a least-squares problem and then it is iteratively updated by minimizing a re-ranking loss. Despite its simplicity, our approach can even surpass soft-prompt learning methods as shown by extensive experiments on 11 image and 2 video datasets.Code available at: https://github.com/saic-fi/LFA

In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. Consistency training has proven to be a powerful semi-supervised learning framework for leveraging unlabeled data under the cluster assumption, in which the decision boundary should lie in low-density regions. In this work, we first observe that for semantic segmentation, the low-density regions are more apparent within the hidden representations than within the inputs. We thus propose cross-consistency training, where an invariance of the predictions is enforced over different perturbations applied to the outputs of the encoder. Concretely, a shared encoder and a main decoder are trained in a supervised manner using the available labeled examples. To leverage the unlabeled examples, we enforce a consistency between the main decoder predictions and those of the auxiliary decoders, taking as inputs different perturbed versions of the encoder's output, and consequently, improving the encoder's representations. The proposed method is simple and can easily be extended to use additional training signal, such as image-level labels or pixel-level labels across different domains. We perform an ablation study to tease apart the effectiveness of each component, and conduct extensive experiments to demonstrate that our method achieves state-of-the-art results in several datasets.