Related papers: Hot-Refresh Model Upgrades with Regression-Allevia…
Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses…
Recent advance in deep learning has led to the rapid adoption of machine learning-based NLP models in a wide range of applications. Despite the continuous gain in accuracy, backward compatibility is also an important aspect for industrial…
In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training.…
Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A common way to improve model robustness is adversarial training…
When machine learning systems meet real world applications, accuracy is only one of several requirements. In this paper, we assay a complementary perspective originating from the increasing availability of pre-trained and regularly…
Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…
Adversarial training has been proven to be an effective technique for improving the adversarial robustness of models. However, there seems to be an inherent trade-off between optimizing the model for accuracy and robustness. To this end, we…
We present Recurrent Fitting (ReFit), a neural network architecture for single-image, parametric 3D human reconstruction. ReFit learns a feedback-update loop that mirrors the strategy of solving an inverse problem through optimization. At…
Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms…
Recent text-to-image generative models, e.g., Stable Diffusion V3 and Flux, have achieved notable progress. However, these models are strongly restricted to their limited knowledge, a.k.a., their own fixed parameters, that are trained with…
When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors. This inconsistent behavior during model upgrade often outweighs the benefits of…
Retrieval Augmented Generation (RAG) is a common method for integrating external knowledge into pretrained Large Language Models (LLMs) to enhance accuracy and relevancy in question answering (QA) tasks. However, prompt engineering and…
Existing methods for image alignment struggle in cases involving feature-sparse regions, extreme scale and field-of-view differences, and large deformations, often resulting in suboptimal accuracy. Robustness to these challenges can be…
Variations of target appearance such as deformations, illumination variance, occlusion, etc., are the major challenges of visual object tracking that negatively impact the performance of a tracker. An effective method to tackle these…
Class Incremental Learning (CIL) constitutes a pivotal subfield within continual learning, aimed at enabling models to progressively learn new classification tasks while retaining knowledge obtained from prior tasks. Although previous…
The remarkable progress in deep learning (DL) showcases outstanding results in various computer vision tasks. However, adaptation to real-time variations in data distributions remains an important challenge. Test-Time Training (TTT) was…
Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL post-training aligns the model with a reward. In image…
In visual search, the gallery set could be incrementally growing and added to the database in practice. However, existing methods rely on the model trained on the entire dataset, ignoring the continual updating of the model. Besides, as the…
Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions. Current methodologies predominantly concentrate on modeling feature interactions…
Minimizing inconsistencies across successive versions of an AI system is as crucial as reducing the overall error. In image classification, such inconsistencies manifest as negative flips, where an updated model misclassifies test samples…