Problem
Research questions and friction points this paper is trying to address.
visual context
forced-choice questions
batch execution
accuracy
efficiency
Visual Jev: Accurate and Efficient Decisions from Shared Visual Context
🤖 AI Summary
该研究通过Visual Jev方法，利用共享视觉上下文一次性编码图像并批量处理问题，提高了决策准确性和效率。
📝 Abstract
Many vision applications ask several independent, forced-choice questions about the same image. Visual Jev encodes the image and public context once, executes isolated question suffixes as a batch, and reads candidate probabilities from the backbone's language-model head. Across four benchmarks, answer-supervised post-training raises equal-weight macro accuracy from 70.6% to 76.1%, with the gain concentrated on the two task families represented in training. At N=32 questions per image, shared batched execution is 8.9x faster in warm amortized time than independent serial execution and remains 3.4x faster than an already-batched baseline that recomputes the prefix, at the cost of higher peak memory. A matched typed-head control offers no consistent accuracy advantage over the language-model-head readout. The supported design is therefore simple: adapt the backbone for quality, retain the existing readout, and share execution for efficiency.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Shared Visual Context
Batch Execution
Language-Model Head
🔎 Similar Papers
No similar papers found.
