Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the latent space of an autoencoder (AE) and produce images by mapping the generated latents into RGB image space using the AE decoder. While this approach allows for efficient model training and sampling, it induces a disconnect between the training of the diffusion model and the decoder, resulting in a loss of detail in the generated images. To remediate this disconnect, we propose to leverage the internal features of the decoder to define a latent perceptual loss (LPL). This loss encourages the models to create sharper and more realistic images. Our loss can be seamlessly integrated with common autoencoders used in latent diffusion models, and can be applied to different generative modeling paradigms such as DDPM with epsilon and velocity prediction, as well as flow matching. Extensive experiments with models trained on three datasets at 256 and 512 resolution show improved quantitative -- with boosts between 6% and 20% in FID -- and qualitative results when using our perceptual loss.

Inspired by the principle of deliberate practice in human learning, we propose Deliberate Practice for Synthetic Data Generation (DP), a novel framework that improves sample efficiency through dynamic synthetic data generation. Prior work has shown that scaling synthetic data is inherently challenging, as naively adding new data leads to diminishing returns. To address this, pruning has been identified as a key mechanism for improving scaling, enabling models to focus on the most informative synthetic samples. Rather than generating a large dataset and pruning it afterward, DP efficiently approximates the direct generation of informative samples. We theoretically show how training on challenging, informative examples improves scaling laws and empirically validate that DP achieves better scaling performance with significantly fewer training samples and iterations. On ImageNet-100, DP generates 3.4x fewer samples and requires six times fewer iterations, while on ImageNet-1k, it generates 8x fewer samples with a 30% reduction in iterations, all while achieving superior performance compared to prior work.

Recent advances in vision language models (VLM) have been driven by contrastive models such as CLIP, which learn to associate visual information with their corresponding text descriptions. However, these models have limitations in understanding complex compositional scenes involving multiple objects and their spatial relationships. To address these challenges, we propose a novel approach that diverges from commonly used strategies that rely on the design of finegrained hard-negative augmentations. Instead, our work focuses on integrating inductive biases into the pretraining of CLIP-like models to improve their compositional understanding. To that end, we introduce a binding module that connects a scene graph, derived from a text description, with a slot-structured image representation, facilitating a structured similarity assessment between the two modalities. We also leverage relationships as text-conditioned visual constraints, thereby capturing the intricate interactions between objects and their contextual relationships more effectively. Our resulting model not only enhances the performance of CLIP-based models in multi-object compositional understanding but also paves the way towards more accurate and sample-efficient image-text matching of complex scenes.

Curation methods for massive vision-language datasets trade off between dataset size and quality. However, even the highest quality of available curated captions are far too short to capture the rich visual detail in an image. To show the value of dense and highly-aligned image-text pairs, we collect the Densely Captioned Images (DCI) dataset, containing 7805 natural images human-annotated with mask-aligned descriptions averaging above 1000 words each. With precise and reliable captions associated with specific parts of an image, we can evaluate vision-language models' (VLMs) understanding of image content with a novel task that matches each caption with its corresponding subcrop. As current models are often limited to 77 text tokens, we also introduce a summarized version (sDCI) in which each caption length is limited. We show that modern techniques that make progress on standard benchmarks do not correspond with significant improvement on our sDCI based benchmark. Lastly, we finetune CLIP using sDCI and show significant improvements over the baseline despite a small training set. By releasing the first human annotated dense image captioning dataset, we hope to enable the development of new benchmarks or finetuning recipes for the next generation of VLMs to come.

Large-scale training of latent diffusion models (LDMs) has enabled unprecedented quality in image generation. However, large-scale end-to-end training of these models is computationally costly, and hence most research focuses either on finetuning pretrained models or experiments at smaller scales. In this work we aim to improve the training efficiency and performance of LDMs with the goal of scaling to larger datasets and higher resolutions. We focus our study on two points that are critical for good performance and efficient training: (i) the mechanisms used for semantic level (\eg a text prompt, or class name) and low-level (crop size, random flip, \etc) conditioning of the model, and (ii) pre-training strategies to transfer representations learned on smaller and lower-resolution datasets to larger ones. The main contributions of our work are the following: we present systematic experimental study of these points, we propose a novel conditioning mechanism that disentangles semantic and low-level conditioning, we obtain state-of-the-art performance on CC12M for text-to-image at 512 resolution.

Self-supervised learning models have been shown to learn rich visual representations without requiring human annotations. However, in many real-world scenarios, labels are partially available, motivating a recent line of work on semi-supervised methods inspired by self-supervised principles. In this paper, we propose a conceptually simple yet empirically powerful approach to turn clustering-based self-supervised methods such as SwAV or DINO into semi-supervised learners. More precisely, we introduce a multi-task framework merging a supervised objective using ground-truth labels and a self-supervised objective relying on clustering assignments with a single cross-entropy loss. This approach may be interpreted as imposing the cluster centroids to be class prototypes. Despite its simplicity, we provide empirical evidence that our approach is highly effective and achieves state-of-the-art performance on CI-FAR100 and ImageNet.

The research in biometric recognition using hand shape has been somewhat stagnating in the last decade. Meanwhile, computer vision and machine learning have experienced a paradigm shift with the renaissance of deep learning, which has set the new state-of-the-art in many related fields. Inspired by successful applications of deep learning for other biometric modalities, we propose a novel approach to 3D hand shape recognition from RGB-D data based on geometric deep learning techniques. We show how to train our model on synthetic data and retain the performance on real samples during test time. To evaluate our method, we provide a new dataset NNHand RGB- D of short video sequences and show encouraging performance compared to diverse baselines on the new data, as well as current benchmark dataset HKPolyU. Moreover, the new dataset opens door to many new research directions in hand shape recognition.