REVIEW 7 cited by
Pix2seq: A Language Modeling Framework for Object Detection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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 pixel inputs. Object descriptions (e.g., bounding boxes and class labels) are expressed as sequences of discrete tokens, and we train a neural network to perceive the image and generate the desired sequence. Our approach is based mainly on the intuition that if a neural network knows about where and what the objects are, we just need to teach it how to read them out. Beyond the use of task-specific data augmentations, our approach makes minimal assumptions about the task, yet it achieves competitive results on the challenging COCO dataset, compared to highly specialized and well optimized detection algorithms.
Forward citations
Cited by 7 Pith papers
-
CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
A chest X-ray VLM co-trained with classification and grounding heads, tuned with DAPO reinforcement learning, and augmented with deterministic measurement tools outperforms prior radiology VLMs on report generation, V...
-
DriveQA: Passing the Driving Knowledge Test
DriveQA is a new multimodal driving-knowledge benchmark showing that LLMs and MLLMs struggle with right-of-way, numerical traffic rules, and sign variations, with modest transfer gains to nuScenes and BDD.
-
SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions
SeqGrowGraph autoregressively generates lane graphs junction-by-junction via a depth-first serialization and reports state-of-the-art topology F1 on nuScenes and Argoverse 2.
-
Parameterized Diffusion Optimization enabled Autoregressive Ordinal Regression for Diabetic Retinopathy Grading
AOR-DR decomposes DR severity grading into conditional binary steps modeled by a diffusion decoder and reports higher accuracy and macro-F1 than six ordinal regression methods on four datasets.
-
ParkFormer: A Transformer-Based Parking Policy with Goal Embedding and Pedestrian-Aware Control
A Transformer parking policy with cross-attention goal fusion and a GRU pedestrian predictor achieves 96.57% success in CARLA parking, but only in simulation with oracle goal and pedestrian states.
-
Style Transfer: A Decade Survey
A broad survey of deep-learning style transfer methods organized by generative model family, with an unvalidated evaluation framework.
-
From Provable Correctness to Probabilistic Generation: A Comparative Review of Program Synthesis Paradigms
A bachelor's thesis surveys deductive, inductive, sketch-based, LLM-based, and neuro-symbolic program synthesis, emphasizing correctness versus usability trade-offs.
Discussion (0). Sign in to comment.