Related papers: DALL-E for Detection: Language-driven Compositiona…

Fully supervised salient object detection (SOD) methods have made considerable progress in performance, yet these models rely heavily on expensive pixel-wise labels. Recently, to achieve a trade-off between labeling burden and performance,…

Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due to limited supervision from image-level labels. To address…

Logo detection in unconstrained images is challenging, particularly when only very sparse labelled training images are accessible due to high labelling costs. In this work, we describe a model training image synthesising method capable of…

We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias…

Deep neural network-based semantic segmentation generally requires large-scale cost extensive annotations for training to obtain better performance. To avoid pixel-wise segmentation annotations which are needed for most methods, recently…

Image composition and generation are processes where the artists need control over various parts of the generated images. However, the current state-of-the-art generation models, like Stable Diffusion, cannot handle fine-grained part-level…

Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. To address this, we propose DenseDiffusion, a…

We propose a novel Auto-Regressive (AR) image generation approach that models images as hierarchical compositions of interpretable visual layers. While AR models have achieved transformative success in language modeling, replicating this…

This work presents a deep object co-segmentation (DOCS) approach for segmenting common objects of the same class within a pair of images. This means that the method learns to ignore common, or uncommon, background stuff and focuses on…

Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such…

Despite significant advancements in text-to-image models for generating high-quality images, these methods still struggle to ensure the controllability of text prompts over images in the context of complex text prompts, especially when it…

Performing data augmentation for learning deep neural networks is well known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

We introduce a method for composing object-level visual prompts within a text-to-image diffusion model. Our approach addresses the task of generating semantically coherent compositions across diverse scenes and styles, similar to the…

We present LlamaSeg, a visual autoregressive framework that unifies multiple image segmentation tasks via natural language instructions. We reformulate image segmentation as a visual generation problem, representing masks as "visual" tokens…

Wireless goal-oriented semantic communication (GSC) has emerged as a promising paradigm by directly optimizing task performance. However, existing GSC frameworks typically operate on entire images and rely on labeled data for classification…

We present GLEE in this work, an object-level foundation model for locating and identifying objects in images and videos. Through a unified framework, GLEE accomplishes detection, segmentation, tracking, grounding, and identification of…

We propose a data-driven approach for context-aware person image generation. Specifically, we attempt to generate a person image such that the synthesized instance can blend into a complex scene. In our method, the position, scale, and…

Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and…

Current deep networks are very data-hungry and benefit from training on largescale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as…

We present Pix2Seq, a simple and generic framework for object detection. Unlike existing approaches that explicitly integrate prior knowledge about the task, we cast object detection as a language modeling task conditioned on the observed…